Instructions to use OrionStarAI/Orion-14B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OrionStarAI/Orion-14B-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OrionStarAI/Orion-14B-Base", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("OrionStarAI/Orion-14B-Base", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use OrionStarAI/Orion-14B-Base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OrionStarAI/Orion-14B-Base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OrionStarAI/Orion-14B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/OrionStarAI/Orion-14B-Base
- SGLang
How to use OrionStarAI/Orion-14B-Base with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "OrionStarAI/Orion-14B-Base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OrionStarAI/Orion-14B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "OrionStarAI/Orion-14B-Base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OrionStarAI/Orion-14B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use OrionStarAI/Orion-14B-Base with Docker Model Runner:
docker model run hf.co/OrionStarAI/Orion-14B-Base
Update modeling_orion.py
#5
by goldbach7 - opened
- modeling_orion.py +2 -2
modeling_orion.py
CHANGED
|
@@ -25,12 +25,12 @@ from transformers.pytorch_utils import ALL_LAYERNORM_LAYERS
|
|
| 25 |
from transformers.utils import (
|
| 26 |
add_start_docstrings,
|
| 27 |
add_start_docstrings_to_model_forward,
|
| 28 |
-
|
| 29 |
logging,
|
| 30 |
replace_return_docstrings,
|
| 31 |
)
|
| 32 |
|
| 33 |
-
if
|
| 34 |
from flash_attn import flash_attn_func, flash_attn_varlen_func
|
| 35 |
from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input # noqa
|
| 36 |
|
|
|
|
| 25 |
from transformers.utils import (
|
| 26 |
add_start_docstrings,
|
| 27 |
add_start_docstrings_to_model_forward,
|
| 28 |
+
is_flash_attn_2_available,
|
| 29 |
logging,
|
| 30 |
replace_return_docstrings,
|
| 31 |
)
|
| 32 |
|
| 33 |
+
if is_flash_attn_2_available():
|
| 34 |
from flash_attn import flash_attn_func, flash_attn_varlen_func
|
| 35 |
from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input # noqa
|
| 36 |
|